.png){kind=icon}
返回
Weighting and pruning based ensemble deep random vector functional link network for tabular data classification
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2022.108879.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we first integrate normalization to the Ensemble Deep Random Vector Functional Link net-work (edRVFL). This re-normalization step can help the network avoid divergence of the hidden features. Then, we propose novel variants of the edRVFL network. Weighted edRVFL (WedRVFL) uses weighting methods to give training samples different weights in different layers according to how the samples were classified confidently in the previous layer thereby increasing the ensemble's diversity and accuracy. Furthermore, a pruning-based edRVFL (PedRVFL) has also been proposed. We prune some inferior neu-rons based on their importance for classification before generating the next hidden layer. Through this method, we ensure that the randomly generated inferior features will not propagate to deeper layers. Subsequently, the combination of weighting and pruning, called Weighting and Pruning based Ensemble Deep Random Vector Functional Link Network (WPedRVFL), is proposed. We compare their performances with other state-of-the-art classification methods on 24 tabular UCI classification datasets. The experi-mental results illustrate the superior performance of our proposed methods. (c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Ensemble deep random vector functional
link (edRVFL)
Weighting methods
Pruning
UCI classification datasets
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Random vector functional link neural network based ensemble deep learning.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容